Related papers: Synaptic efficacy shapes resource limitations in w…

State space models (SSMs) have gained attention by showing potential to outperform Transformers. However, previous studies have not sufficiently addressed the mechanisms underlying their high performance owing to a lack of theoretical…

This paper gives an overview of recent progress in the brain inspired computing field with a focus on implementation using emerging memories as electronic synapses. Design considerations and challenges such as requirements and design…

Synapses are information efficient in the sense that their natural conductance values convey as many bits per Joule as possible, but efficiency falls rapidly if the conductance is forced to deviate from its natural value (Harris et al,…

We simulate static memory materials on a two-dimensional lattice. The bulk properties of such materials depend on boundary conditions. Considerable information can be stored in various local patterns. We observe local probabilities…

It is known that fiber nonlinearities induce crosstalk in a wavelength division multiplexed (WDM) system, which limits the capacity of such systems as the transmitted signal power is increased. A network user in a WDM system is an entity…

Topographic maps are a brain structure connecting pre-synpatic and post-synaptic brain regions. Topographic development is dependent on Hebbian-based plasticity mechanisms working in conjunction with spontaneous patterns of neural activity…

It is believed that hippocampus functions as a memory allocator in brain, the mechanism of which remains unrevealed. In Valiant's neuroidal model, the hippocampus was described as a randomly connected graph, the computation on which maps…

Efficient network packet processing increasingly demands dynamic, adaptive, and run-time resizable match table allocation to handle the diverse and heterogeneous nature of traffic patterns and rule sets. Achieving this flexibility at high…

We develop a novel mathematical programming approximation framework to tackle the stochastic knapsack problem. In this problem, the decision maker considers items for which either weights or values, or both, are random. The aim is to select…

The memory demands of large-scale deep neural networks (DNNs) require synaptic weight values to be stored and updated in off-chip memory like dynamic random-access memory, which reduces energy efficiency and increases training time.…

This work reports a compact behavioral model for gated-synaptic memory. The model is developed in Verilog-A for easy integration into computer-aided design of neuromorphic circuits using emerging memory. The model encompasses various forms…

Recent research has established a connection between modern Hopfield networks (HNs) and transformer attention heads, with guarantees of exponential storage capacity. However, these models still face challenges scaling storage efficiently.…

We give algorithms with constant-factor performance guarantees for several capacity and throughput problems in the SINR model. The algorithms are all based on a novel LP formulation for capacity problems. First, we give a new…

We study the trade-offs between storage/bandwidth and prediction accuracy of neural networks that are stored in noisy media. Conventionally, it is assumed that all parameters (e.g., weight and biases) of a trained neural network are stored…

We propose a learning-based framework for efficient power allocation in ad hoc interference networks under episodic constraints. The problem of optimal power allocation -- for maximizing a given network utility metric -- under instantaneous…

Exactly solvable neural network models with asymmetric weights are rare, and exact solutions are available only in some mean-field approaches. In this article we find exact analytical solutions of an asymmetric spin-glass-like model of…

On-device training has become an increasingly popular approach to machine learning, enabling models to be trained directly on mobile and edge devices. However, a major challenge in this area is the limited memory available on these devices,…

The long-term memory of most connectionist systems lies entirely in the weights of the system. Since the number of weights is typically fixed, this bounds the total amount of knowledge that can be learned and stored. Though this is not…

Working memory is a central cognitive ability crucial for intelligent decision-making. Recent experimental and computational work studying working memory has primarily used categorical (i.e., one-hot) inputs, rather than ecologically…

Humans and artificial agents must often learn and switch between multiple tasks in dynamic environments. Success in such settings requires cognitive flexibility: the ability to retain prior knowledge (cognitive stability) while also…